Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 23637
    Prev
    Next
    INDEX
    Explanations

    terms related to different ownership types of organizations, specifically focusing on private ownership

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ownership and governance, particularly distinguishing between private and public entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arella
    -0.85
    oons
    -0.71
    eln
    -0.69
    iom
    -0.69
    antics
    -0.69
    raltar
    -0.68
     Parenthood
    -0.68
     Payne
    -0.67
    amia
    -0.67
    iens
    -0.67
    POSITIVE LOGITS
     sourced
    1.11
     funded
    1.04
     constructed
    1.04
     situated
    1.03
     produced
    1.03
     financed
    1.03
     configured
    1.03
     distributed
    1.02
     generated
    1.02
     appointed
    1.02
    Activations Density 0.113%

    No Known Activations